Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
校外培训机构资质与教师备案核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language ledger checker whose disclosed behavior matches its files and does not show hidden network, persistence, or destructive activity.
Install this only if you are comfortable running a local Node-based checker over potentially sensitive institutional ledger data. It does not appear to send data out, but it also does not verify official certificate authenticity or replace local regulator review.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill’s natural-language interface and outputs are explicitly written in Chinese, beginning with the file description and continuing throughout user-facing messages. There is no indication that users can choose another language or locale, which may violate a language/locale choice policy.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
The file consists entirely of Chinese-language labels and content, with no indication that the skill offers language selection or that the locale restriction is intentionally limited to a Chinese-region use case. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The header comments state that in the free package the withheld checks are removed and only explanatory text remains, yet later constants and output text include substantive premium-check scope statements such as built-in 2026 'double reduction' timing rules in
OUT_OF_SCOPE/summary.basis. This is not execution of the premium checks, but the documentation's framing that only inert explanation text remains is broader than what the file actually contains and emits.- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The manifest describes the free skill as performing six free audit items, but the code also embeds five additional paid-check descriptions and returns them in
checks_withheld/checks_not_runoutput fields. While it does not execute those checks, the behavior goes beyond a narrowly scoped checker by advertising extra premium capabilities in runtime results.- Content
Static analysis
No suspicious patterns detected.